skills/michaelmerrill/skills/design/Gen Agent Trust Hub

design

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, security vulnerabilities, or policy violations were detected within the skill's instructions, metadata, or evaluation cases.
  • [PROMPT_INJECTION]: The skill follows a structured interview protocol for UX design. There are no instructions to bypass safety guidelines, override system behavior, or extract sensitive system prompts.
  • [DATA_EXFILTRATION]: No network-enabled tools or hardcoded credentials were identified. The skill's file system interaction is limited to reading from the ./plans/ directory and searching for documentation (READMEs, style guides) within the local project structure to maintain the 'living document'.
  • [COMMAND_EXECUTION]: The skill does not invoke shell commands, subprocesses, or dynamic execution environments. It utilizes the AskUserQuestion tool for interaction and writes content back to local markdown files using a predefined template.
  • [EXTERNAL_DOWNLOADS]: No external scripts, packages, or remote code patterns were detected. All dependencies are internal to the skill's repository (e.g., the markdown template in assets/).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 10:30 PM